{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:11:43Z","timestamp":1774311103346,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032213204","type":"print"},{"value":"9783032213211","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-21321-1_62","type":"book-chapter","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T11:06:16Z","timestamp":1774263976000},"page":"610-625","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BioGraphletQA: Knowledge-Anchored Generation of\u00a0Complex QA Datasets"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3806-6940","authenticated-orcid":false,"given":"Richard A. A.","family":"Jonker","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5183-2469","authenticated-orcid":false,"given":"B\u00e1rbara Maria Ribeiro de Abreu","family":"Martins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1941-3983","authenticated-orcid":false,"given":"S\u00e9rgio","family":"Matos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"62_CR1","unstructured":"Banerjee, D., Awale, S., Usbeck, R., Biemann, C.: DBLP-quad: a question answering dataset over the DBLP scholarly knowledge graph. arXiv preprint arXiv:2303.13351 (2023)"},{"key":"62_CR2","unstructured":"Bao, J., Duan, N., Yan, Z., Zhou, M., Zhao, T.: Constraint-based question answering with knowledge graph. In: Matsumoto, Y., Prasad, R. (eds.) Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2503\u20132514. The COLING 2016 Organizing Committee, Osaka, Japan (2016). https:\/\/aclanthology.org\/C16-1236\/"},{"key":"62_CR3","doi-asserted-by":"crossref","unstructured":"Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pp. 1247\u20131250 (2008)","DOI":"10.1145\/1376616.1376746"},{"issue":"1","key":"62_CR4","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1038\/s41597-023-02757-0","volume":"10","author":"M Boudin","year":"2023","unstructured":"Boudin, M., Diallo, G., Dranc\u00e9, M., Mougin, F.: The oregano knowledge graph for computational drug repurposing. Sci. data 10(1), 871 (2023)","journal-title":"Sci. data"},{"key":"62_CR5","doi-asserted-by":"crossref","unstructured":"Braga, M., Kasela, P., Raganato, A., Pasi, G.: Synthetic data generation with large language models for personalized community question answering. arXiv preprint arXiv:2410.22182 (2024)","DOI":"10.1109\/WI-IAT62293.2024.00057"},{"key":"62_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-01960-3","author":"P Chandak","year":"2023","unstructured":"Chandak, P., Huang, K., Zitnik, M.: Building a knowledge graph to enable precision medicine. Nature Sci. Data (2023). https:\/\/doi.org\/10.1038\/s41597-023-01960-3","journal-title":"Nature Sci. Data"},{"key":"62_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-030-30796-7_5","volume-title":"The Semantic Web \u2013 ISWC 2019","author":"M Dubey","year":"2019","unstructured":"Dubey, M., Banerjee, D., Abdelkawi, A., Lehmann, J.: LC-QuAD 2.0: A Large Dataset for Complex Question Answering over Wikidata and DBpedia. In: Ghidini, C., et al. (eds.) ISWC 2019. LNCS, vol. 11779, pp. 69\u201378. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30796-7_5"},{"key":"62_CR8","doi-asserted-by":"crossref","unstructured":"Dutt, R., Khosla, S., Kumar, V.B., Gangadharaiah, R.: Grailqa++: a challenging zero-shot benchmark for knowledge base question answering. In: Proceedings of the 13th IJCNLP, pp. 897\u2013909 (2023)","DOI":"10.18653\/v1\/2023.ijcnlp-main.58"},{"key":"62_CR9","doi-asserted-by":"crossref","unstructured":"Gu, Y., et al.: Beyond IID: three levels of generalization for question answering on knowledge bases. In: Proceedings of the Web Conference 2021, pp. 3477\u20133488 (2021)","DOI":"10.1145\/3442381.3449992"},{"key":"62_CR10","unstructured":"Haas, R.: A survey of biomedical knowledge graphs and of resources for their construction (2024) https:\/\/robert-haas.github.io\/awesome-biomedical-knowledge-graphs\/"},{"key":"62_CR11","doi-asserted-by":"publisher","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst. 43(2) (2025). https:\/\/doi.org\/10.1145\/3703155","DOI":"10.1145\/3703155"},{"key":"62_CR12","doi-asserted-by":"publisher","unstructured":"Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12) (2023).https:\/\/doi.org\/10.1145\/3571730","DOI":"10.1145\/3571730"},{"key":"62_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, L., Usbeck, R.: Knowledge graph question answering datasets and their generalizability: are they enough for future research? In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 3209\u20133218 (2022)","DOI":"10.1145\/3477495.3531751"},{"key":"62_CR14","doi-asserted-by":"crossref","unstructured":"Jin, D., Pan, E., Oufattole, N., Weng, W.H., Fang, H., Szolovits, P.: What disease does this patient have? a large-scale open domain question answering dataset from medical exams (2020). https:\/\/arxiv.org\/abs\/2009.13081","DOI":"10.20944\/preprints202105.0498.v1"},{"key":"62_CR15","doi-asserted-by":"publisher","unstructured":"Jin, Q., Dhingra, B., Liu, Z., Cohen, W., Lu, X.: PubMedQA: a dataset for biomedical research question answering. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 2567\u20132577. Association for Computational Linguistics, Hong Kong, China (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1259, https:\/\/aclanthology.org\/D19-1259\/","DOI":"10.18653\/v1\/D19-1259"},{"key":"62_CR16","doi-asserted-by":"publisher","unstructured":"Li, D., Jiang, B., Huang, L., Beigi, A., Zhao, C., Tan, Z., Bhattacharjee, A., Jiang, Y., Chen, C., Wu, T., Shu, K., Cheng, L., Liu, H.: From generation to judgment: Opportunities and challenges of LLM-as-a-judge. In: Christodoulooulos, C., Chakraborty, T., Roe, C., Peng, V. (eds.) Proceedings of the 2025 Conference on Empirical Methods in atural Language Processing, pp. 2757\u20132791. Association for Computational Linguistics, Suzhou, China (2025). https:\/\/doi.org\/10.18653\/v1\/2025.emnlp-main.138, https:\/\/aclanthology.org\/2025.emnlp-main.138\/","DOI":"10.18653\/v1\/2025.emnlp-main.138"},{"key":"62_CR17","unstructured":"Namboori, A., Mangale, S., Rosenbaum, A., Soltan, S.: Gemquad: generating multilingual question answering datasets from large language models using few shot learning. arXiv preprint arXiv:2404.09163 (2024)"},{"key":"62_CR18","doi-asserted-by":"publisher","unstructured":"Peixoto, T.P.: The graph-tool python library. figshare (2014). https:\/\/doi.org\/10.6084\/m9.figshare.1164194, http:\/\/figshare.com\/articles\/graph_tool\/1164194","DOI":"10.6084\/m9.figshare.1164194"},{"key":"62_CR19","doi-asserted-by":"publisher","unstructured":"Pradeep, R., et al.: ConvKGYarn: spinning configurable and scalable conversational knowledge graph QA datasets with large language models. In: Dernoncourt, F., Preo\u0163iuc-Pietro, D., Shimorina, A. (eds.) Poceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pp. 1176\u20131206. Association for Computational Linguistics, Miami, Florida, US (Nov 2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-industry.89, https:\/\/aclanthology.org\/2024.emnlp-industry.89\/","DOI":"10.18653\/v1\/2024.emnlp-industry.89"},{"key":"62_CR20","doi-asserted-by":"publisher","unstructured":"Putman, T.E., et al.: The monarch initiative in 2024: an analytic platform integrating phenotypes, genes and diseases across species. Nucleic Acids Res. 52(D1), D938\u2013D949 (2023). https:\/\/doi.org\/10.1093\/nar\/gkad1082","DOI":"10.1093\/nar\/gkad1082"},{"issue":"2","key":"62_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3433652","volume":"54","author":"P Ribeiro","year":"2021","unstructured":"Ribeiro, P., Paredes, P., Silva, M.E., Aparicio, D., Silva, F.: A survey on subgraph counting: concepts, algorithms, and applications to network motifs and graphlets. ACM comput. surv. (CSUR) 54(2), 1\u201336 (2021)","journal-title":"ACM comput. surv. (CSUR)"},{"key":"62_CR22","doi-asserted-by":"crossref","unstructured":"Robertson, S., et\u00a0al.: The probabilistic relevance framework: Bm25 and beyond. Found. Trends\u00ae Inf. Retrieval 3(4), 333\u2013389 (2009)","DOI":"10.1561\/1500000019"},{"issue":"5","key":"62_CR23","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1038\/s41587-021-01145-6","volume":"40","author":"A Santos","year":"2022","unstructured":"Santos, A., et al.: A knowledge graph to interpret clinical proteomics data. Nat. Biotechnol. 40(5), 692\u2013702 (2022)","journal-title":"Nat. Biotechnol."},{"key":"62_CR24","doi-asserted-by":"publisher","unstructured":"Sayers, E.W., et al.: Database resources of the national center for biotechnology information. Nucleic Acids Res. 49(D1), D10\u2013D17 (2020). https:\/\/doi.org\/10.1093\/nar\/gkaa892, https:\/\/doi.org\/10.1093\/nar\/gkaa892","DOI":"10.1093\/nar\/gkaa892"},{"key":"62_CR25","unstructured":"Tang, R., Han, X., Jiang, X., Hu, X.: Does synthetic data generation of LLMs help clinical text mining? arXiv preprint arXiv:2303.04360 (2023)"},{"key":"62_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. vol.\u00a030 (2017)"},{"issue":"10","key":"62_CR27","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78\u201385 (2014)","journal-title":"Commun. ACM"},{"issue":"4","key":"62_CR28","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1109\/TCBB.2006.51","volume":"3","author":"S Wernicke","year":"2006","unstructured":"Wernicke, S.: Efficient detection of network motifs. IEEE\/ACM Trans. Comput. Biol. Bioinf. 3(4), 347\u2013359 (2006). https:\/\/doi.org\/10.1109\/TCBB.2006.51","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"62_CR29","unstructured":"Wu, I., et al.: Synthetic multimodal question generation. arXiv preprint arXiv:2407.02233 (2024)"},{"key":"62_CR30","unstructured":"Xu, C., Guan, S., Greene, D., Kechadi, M.T.: Benchmark data contamination of large language models: a survey (2024). https:\/\/arxiv.org\/abs\/2406.04244"},{"key":"62_CR31","doi-asserted-by":"crossref","unstructured":"Yan, X., Westphal, P., Seliger, J., Usbeck, R.: Bridging the gap: generating a comprehensive biomedical knowledge graph question answering dataset. In: ECAI 2024, pp. 1198\u20131205. IOS Press (2024)","DOI":"10.3233\/FAIA240615"},{"key":"62_CR32","unstructured":"Yang, A., et al.: Qwen3 technical report (2025). https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"62_CR33","doi-asserted-by":"crossref","unstructured":"Yasunaga, M., Leskovec, J., Liang, P.: Linkbert: pretraining language models with document links. In: Association for Computational Linguistics (ACL) (2022)","DOI":"10.18653\/v1\/2022.acl-long.551"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21321-1_62","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:18:41Z","timestamp":1774307921000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21321-1_62"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032213204","9783032213211"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21321-1_62","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"24 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}